Modeling of sows diurnal activity pattern and detection of parturition using acceleration measurements

This article suggests and assesses two different monitoring methods for detecting sows parturition using series of three-dimensions acceleration measurements previously classified into activity types. Two groups of sows are monitored: a first group (n=9) provided with straw (S), and a second group (n=10) where no straw is provided (NS); two types of activity are taken into account: high active behaviour (corresponding to feeding, rooting and nest building behaviours) and total active behaviour (including any active activity type). The first method suggests modeling sows' diurnal pattern of activity using a saw-tooth function for the probability of being active and monitoring the series using a Dynamic Generalized Linear Model (DGLM). The second method is based on a cumulative sum of hourly differences of activity, from day-to-day. Both methods use a threshold value, optimized for each group, to detect the onset of farrowing. Best results in terms of sensitivity and specificity are observed for the cumulative sum method, using individual variance and monitoring high active (sensitivity=100%; specificity=100%) and total active behaviours (sensitivity=100%; specificity=95%). Results of the DGLM method indicate a sensitivity of 100% and a specificity of 89% in average for both group S and NS. Observing the occurrence of alarm times, the DGLM method allows (i) earlier detection of farrowing: 15h before the onset of farrowing, for both groups, as compared to 9-12 for the other methods; and (ii) a better distribution of alarms, i.e. minimize the number of alarms occurring within the last 6h before farrowing.

[1]  Cécile Cornou,et al.  Original papers: Modelling and monitoring sows' activity types in farrowing house using acceleration data , 2011 .

[2]  Cécile Cornou,et al.  Classification of sows' activity types from acceleration patterns using univariate and multivariate models , 2010 .

[3]  L. Bate,et al.  Increasing piglet survival through an improved farrowing management protocol , 1996 .

[4]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[5]  Harold W. Gonyou,et al.  Increasing available space in a farrowing crate does not facilitate postural changes or maternal responses in gilts , 1998 .

[6]  Michael A. West,et al.  Bayesian Forecasting and Dynamic Models (2nd edn) , 1997, J. Oper. Res. Soc..

[7]  B Erez,et al.  A microcomputer-photocell system to monitor periparturient activity of sows and transfer data to remote location. , 1990, Journal of animal science.

[8]  J. Rushen,et al.  Preparturient variation in progesterone, prolactin, oxytocin and somatostatin in relation to nest building in sows , 1993 .

[9]  Cécile Cornou,et al.  Modeling and monitoring sows' activity types in the farrowing house using 3D acceleration data , 2011 .

[10]  K. Triantafyllopoulos.  Inference of Dynamic Generalized Linear Models: On‐Line Computation and Appraisal , 2009 .

[11]  M. West,et al.  Bayesian forecasting and dynamic models , 1989 .

[12]  Cécile Cornou,et al.  Classifying sows' activity types from acceleration patterns An application of the Multi-Process Kalman Filter , 2008 .

[13]  B. Algers,et al.  Maternal behavior in pigs , 2007, Hormones and Behavior.

[14]  Stanley Lemeshow,et al.  Applied Logistic Regression, Second Edition , 1989 .

[15]  H.P.M. Bressers,et al.  Monitoring individual sows: radiotelemetrically recorded ear base temperature changes around farrowing , 1994 .

[16]  Jukka Heikkonen,et al.  Using movement sensors to detect the onset of farrowing , 2008 .

[17]  J. Rushen,et al.  Evidence of a limited role for prolactin in the preparturient activity of confined gilts. , 2001, Applied animal behaviour science.

[18]  T G Hartsock,et al.  Prepartum behavior in swine: effects of pen size. , 1997, Journal of animal science.

[19]  Xavier Manteca,et al.  Validation of an automatic system to detect position changes in puerperal sows , 2009 .